A high-precision energy monitoring system and abnormal monitoring data processing method

Abstract

The present invention relates to the field of energy monitoring technology, and in particular to a high-precision energy monitoring system and an abnormal monitoring data processing method. The method determines the hazard factor of natural gas combustion products based on the combustion product emission monitoring data of natural gas combustion products; determines the degree of abnormal hazard of natural gas combustion products based on the natural gas combustion products at different times; constructs an isolation tree of natural gas fuel products based on the combustion product emission monitoring data; adjusts the path length of the isolation tree of natural gas fuel products based on the degree of abnormal hazard; obtains the abnormal score of the natural gas combustion product corresponding to each data point through the isolation tree, and determines the abnormal data in the natural gas combustion products based on the abnormal score. The present invention improves the accuracy of abnormal detection and reduces the occurrence of misjudgment.

Description

Technical Field

[0001] The present invention relates to the technical field of energy monitoring, and in particular to a high-precision energy monitoring system and an abnormal monitoring data processing method. Background Art

[0002] With the increase in energy demand and the improvement in energy utilization efficiency, the importance of energy anomaly monitoring technology in the power system has become increasingly prominent; as a relatively clean fossil energy, natural gas can contribute to reducing overall carbon emissions and achieving energy conservation and emission reduction goals if its combustion efficiency can be improved and waste and pollution emissions can be reduced; the anomaly monitoring system can monitor key data such as the composition of natural gas combustion products in real time, and can quickly discover abnormal hazards and energy waste of combustion products caused by incomplete combustion during the combustion process, so it is very important to monitor the combustion products of natural gas.

[0003] When monitoring natural gas combustion product emissions, factors such as equipment failure, overload and external interference often lead to sudden abnormalities in the combustion product emission monitoring data. When processing such data, the traditional isolation forest algorithm usually uses the same weight to calculate the average path length of data points in all isolated trees and then evaluate their abnormality. However, this method ignores the key role of combustion product emission monitoring data with a high degree of abnormality in anomaly detection. These combustion product emission monitoring data with high abnormality can often quickly and accurately capture the key information of abnormal characteristics, but the traditional algorithm fails to give them enough weight, resulting in the failure of these key information to play a full role. Therefore, the isolation tree that performs well in the abnormal mode fails to receive due attention in the calculation of the final anomaly score, which may cause the real abnormal data to be misjudged as normal data, posing a potential threat to the safe and stable operation of natural gas combustion product emissions. Summary of the invention

[0004] In order to solve the technical problem that there may be misjudgment when using the traditional isolation forest algorithm to evaluate data anomalies, the purpose of the present invention is to provide a high-precision energy monitoring system and an abnormal monitoring data processing method. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for processing high-precision energy anomaly monitoring data, the method comprising:

[0006] Obtain combustion product emission monitoring data during the emission of different types of natural gas combustion products;

[0007] Determine the hazard factors of natural gas combustion products based on the monitoring data of combustion product emissions of natural gas combustion products;

[0008] According to the types of natural gas combustion products at different times, historical moments are divided into strong contrast moments and weak contrast moments; according to the constraint relationship between natural gas combustion products at weak contrast moments and the number of types of natural gas combustion processes, some weak contrast moments are divided into strong contrast moments; according to the time difference and temperature difference of the strong contrast moments, the confidence level of the strong contrast moments is determined; and the abnormal degree of the hazard of the natural gas combustion products is determined by combining the hazard factor and the confidence level;

[0009] Based on the combustion product emission monitoring data, an isolation tree of natural gas fuel products is constructed; according to the abnormal degree of the hazard, the path length of the isolation tree of the natural gas fuel products is adjusted; the abnormal score of the natural gas combustion products corresponding to each data point is obtained through the isolation tree, and the abnormal data in the natural gas combustion products is determined according to the abnormal score.

[0010] Furthermore, the determining of the hazard factors of the natural gas combustion products according to the combustion product emission monitoring data of the natural gas combustion products includes:

[0011] The combustion product emission monitoring data includes: temperature data during the natural gas combustion product emission process, concentration data and activity values ​​of different types of natural gas combustion product gases;

[0012] The temperature data, the activity value and the proportion of the concentration data in the concentration data of all natural gas combustion product gases are multiplied together, and the obtained product value is used as the hazard factor of the natural gas combustion product.

[0013] Furthermore, the historical moments are divided into strong contrast moments and weak contrast moments according to the types of natural gas combustion products at different moments, including:

[0014] Take any historical moment as the moment to be analyzed. When the type of natural gas combustion products corresponding to the moment to be analyzed is consistent with that at the current sampling moment, the moment to be analyzed is taken as a strong contrast moment; when the type of natural gas combustion products corresponding to the moment to be analyzed is inconsistent with that at the current sampling moment, the moment to be analyzed is taken as a weak contrast moment.

[0015] Furthermore, according to the constraint relationship between the natural gas combustion products at the weak contrast moments and the number of types of the natural gas combustion process, some weak contrast moments are divided into strong contrast moments, including:

[0016] Analyze the restriction relationship between the concentrations of different natural gas combustion products and determine the relevant restriction degree between different natural gas combustion products;

[0017] According to the mutual restraint degree of natural gas combustion products and the number of types of natural gas combustion processes at the weak contrast moment, the comparison reference of the weak contrast moment is determined;

[0018] When the contrast reference of the weak contrast moment is greater than or equal to the preset contrast threshold, the weak contrast moment is classified as a strong contrast moment.

[0019] Furthermore, the analysis of the constraint relationship between the concentrations of different natural gas combustion products and the determination of the correlation constraint degree between the different natural gas combustion products include:

[0020] For any two natural gas combustion products, the difference in the number of extreme value points of the historical concentration data curves of the two natural gas combustion products is analyzed to determine the constrained fluctuation difference;

[0021] Calculate the cumulative sum of the time differences corresponding to the extreme values ​​of the same order in the concentration data curves of the two natural gas combustion products as the constrained time difference;

[0022] A negative correlation mapping is performed on the product value of the constraint fluctuation difference and the constraint time difference to obtain the correlation constraint degree between the two natural gas combustion products.

[0023] Furthermore, the calculation formula of the comparison reference at the weak contrast moment is:

[0024] ;

[0025] Among them, norm is the normalization function; is the number of natural gas combustion products of the same type between the i-th sampling moment and the m-th weak comparison moment; is the number of different types of natural gas combustion products between the i-th sampling moment and the m-th weak comparison moment; is the mutual restriction degree between the ath natural gas combustion product of the same type and the bth natural gas combustion product of different type at the i-th sampling moment; is the mutual restriction degree between the a-th natural gas combustion product of the same type and the b-th natural gas combustion product of different type at the m-th weak contrast moment corresponding to the ith sampling moment; To take the absolute value sign.

[0026] Further, determining the confidence level of the strong contrast moment according to the time difference and temperature difference of the strong contrast moment includes:

[0027] The product of the time difference and the temperature difference at the strong contrast moment and the current moment is calculated as the initial deviation degree; the initial deviation degree is negatively correlated and mapped to obtain the confidence level of the strong contrast moment.

[0028] Further, adjusting the path length of the isolated tree of the natural gas fuel product according to the abnormal degree of the hazard includes:

[0029] The mean value of the abnormal degree of hazard of the layer to which the data point corresponding to each natural gas combustion product belongs in the isolated tree is used as the negative correlation mapping value of the weighted value, and the path length of the data point corresponding to each natural gas combustion product in the isolated tree is weighted to obtain the weighted path length of the data point corresponding to each natural gas combustion product in the isolated tree. The weighted path length is the path length of the isolated tree of the adjusted natural gas fuel product.

[0030] Further, determining abnormal data in the natural gas combustion products according to the abnormality score includes:

[0031] Taking any sampling moment as the target sampling moment, taking the average of the abnormal scores of the corresponding data points of the combustion product emission monitoring data of all types of natural gas combustion product emission processes at the target sampling moment as the moment abnormal score of the target sampling moment; when the moment abnormal score is greater than or equal to the preset abnormal threshold, the combustion product emission monitoring data at the target sampling moment is determined to be suspected abnormal data;

[0032] If the proportion of suspected abnormal data in the combustion product emission monitoring data at the target sampling moment and the combustion product emission monitoring data at the corresponding historical moment is greater than or equal to one half, the combustion product emission monitoring data at the sampling moment shall be recorded as abnormal data.

[0033] In a second aspect, a high-precision energy monitoring system is provided, the system comprising the following modules:

[0034] A data monitoring module is used to obtain combustion product emission monitoring data during the emission of different types of natural gas combustion products;

[0035] A first data analysis module is used to determine the hazard factor of the natural gas combustion products according to the combustion product emission monitoring data of the natural gas combustion products;

[0036] The second data analysis module is used to divide the historical moments into strong contrast moments and weak contrast moments according to the types of natural gas combustion products at different moments; divide some weak contrast moments into strong contrast moments according to the constraint relationship between natural gas combustion products at weak contrast moments and the number of types of natural gas combustion processes; determine the confidence level of the strong contrast moments according to the time difference and temperature difference of the strong contrast moments; and determine the abnormal degree of the hazard of the natural gas combustion products in combination with the hazard factor and the confidence level;

[0037] The anomaly monitoring module is used to construct an isolation tree of natural gas fuel products based on combustion product emission monitoring data; adjust the path length of the isolation tree of natural gas fuel products according to the degree of hazard anomaly; obtain the anomaly score of the natural gas combustion products corresponding to each data point through the isolation tree, and determine the abnormal data in the natural gas combustion products based on the anomaly score.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, various possible embodiments of the first aspect are implemented.

[0039] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0040] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute various possible implementations of the first aspect.

[0041] The embodiments of the present invention have at least the following beneficial effects:

[0042] The confidence level of each combustion product emission monitoring data at any time is evaluated by comparing the data deviation between the combustion product emission monitoring data and its historical moment. The confidence level of all historical data of different combustion product emission monitoring data is used, combined with the hazard factors obtained by analyzing the combustion product emission monitoring data, to evaluate the hazard anomaly level of different combustion product emission monitoring data. In the process of constructing the isolated tree, the randomness of the traditional isolation forest algorithm is maintained, and a new weight allocation mechanism is further introduced based on the hazard anomaly level. The path length of the data point in the isolated tree is adjusted according to the path length of the data point in the isolated tree and the hazard anomaly level of the combustion product emission monitoring data of the data point on its layer, so that the highly abnormal combustion product emission monitoring data is located in the top-level isolated tree and is given a larger weight. Then, when obtaining the anomaly score of the natural gas combustion product corresponding to the data point, these isolated trees with high anomaly levels will play a greater role, and can segment the abnormal features earlier, reduce the misjudgment, and thus significantly improve the accuracy of anomaly detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A method flow chart of a high-precision energy anomaly monitoring data processing method provided by an embodiment of the present invention;

[0045] Figure 2 A flow chart of a method for determining the degree of abnormal hazards of natural gas combustion products provided by one embodiment of the present invention;

[0046] Figure 3 A flow chart of a method for dividing some weak-contrast moments into strong-contrast moments provided by an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation method, structure, characteristics and effects of a high-precision energy monitoring system and abnormal monitoring data processing method proposed in accordance with the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0049] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0050] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0051] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0052] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0053] The embodiments of the present invention are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0054] The embodiment of the present invention provides a specific implementation method of a high-precision energy monitoring system and an abnormal monitoring data processing method, which is applicable to various types of natural gas combustion product emission processes.

[0055] The specific scheme of a high-precision energy anomaly monitoring data processing method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0056] See also Figure 1 , which shows a flowchart of a method for processing high-precision energy anomaly monitoring data provided by an embodiment of the present invention, the method comprising the following steps:

[0057] Step S100, obtaining combustion product emission monitoring data during the emission of different types of natural gas combustion products.

[0058] The combustion product emission monitoring data of different types of natural gas combustion product emission processes include: temperature data of natural gas combustion product emission processes, concentration data and activity values ​​of different types of natural gas combustion product gases.

[0059] Temperature sensors and gas analyzers are installed at key locations of the natural gas combustion product emission outlet; the temperature sensors and gas analyzers can obtain temperature data during the natural gas combustion product emission process and concentration data of different types of natural gas combustion product gases in real time.

[0060] Among them, in the present invention, every second is preset as a collection time, and in other embodiments, the collection time can be adjusted by the implementer according to the actual situation. In the embodiment of the present invention, the combustion product emission monitoring data of the natural gas combustion product emission process is collected for 4 hours. The data sequence composed of the temperature data at all the collection times is used as the combustion product emission temperature data sequence during the natural gas combustion product emission process; the data sequence composed of the concentration data of different types of natural gas combustion products at all the collection times is used as the natural gas combustion product concentration data sequence.

[0061] The gas chromatography gas composition analysis technology is used to analyze each natural gas combustion product at each sampling time to obtain the activity value of each natural gas combustion product.

[0062] Step S200, determining the hazard factors of natural gas combustion products according to the combustion product emission monitoring data of the natural gas combustion products.

[0063] The concentration and composition of natural gas combustion products usually fluctuate greatly, which may be due to external factors such as weather and industrial activities. This makes the hazard factors may not accurately reflect the long-term or actual environmental conditions; and the change in the concentration of natural gas combustion products may be only temporary. The assessment at a single moment may not capture the long-term trend or certain potential hazards; historical data provides the fluctuation of the concentration of natural gas combustion products in different time periods, which can help evaluate the trend of hazard changes under different temperature environments.

[0064] Due to the various natural gas combustion products emitted during the combustion and production process of industrial enterprises, the degree of harm of these different types of natural gas combustion products is also different. The harm is mainly reflected in their activity. The more active the natural gas combustion product, the easier it is to undergo chemical reactions and cause harm to the air; and the activity of natural gas combustion products is different under different temperature environments. The higher the temperature, the higher the activity of the gas, which will increase the degree of harm to the air; therefore, by analyzing the fuel product emission monitoring data of each natural gas combustion product at each sampling moment, the hazard factor of the natural gas combustion product is determined. Among them, step S100 has stated that the combustion product emission monitoring data includes: temperature data during the natural gas combustion product emission process, concentration data and activity values ​​of different types of natural gas combustion product gases, which will not be repeated here.

[0065] The greater the activity value of the natural gas combustion products, the more active the natural gas combustion products are, and the easier it is to undergo chemical reactions, causing harm to the air; the higher the temperature during the emission process of the natural gas combustion products, the greater the activity of the natural gas combustion products, which in turn will increase the degree of harm to the air; the greater the concentration of the natural gas combustion products, the more reaction gas can be produced, and the greater the degree of harm to the air.

[0066] The method for obtaining the hazard factor is: multiplying the proportion of the temperature data, the activity value and the concentration data in the concentration data of all natural gas combustion product gases, and obtaining the product value as the hazard factor of the natural gas combustion product.

[0067] In some embodiments, the calculation formula for the hazard factor of natural gas combustion products is:

[0068] ;

[0069] in, is the hazard factor of the jth natural gas combustion product at the i-th collection time; is the temperature data at the i-th collection moment; is the activity value of the j-th natural gas combustion product at the i-th collection time; is the concentration data of the j-th natural gas combustion product at the i-th collection time; is the total concentration of all natural gas combustion products at the i-th acquisition moment; It is the proportion of the concentration data of the j-th natural gas combustion product at the ith collection moment in the concentration data of all natural gas combustion product gases.

[0070] Step S300, according to the types of natural gas combustion products at different times, the historical moments are divided into strong contrast moments and weak contrast moments; according to the constraint relationship between the natural gas combustion products at the weak contrast moments and the number of types of the natural gas combustion process, some weak contrast moments are divided into strong contrast moments; according to the time difference and temperature difference of the strong contrast moments, the confidence level of the strong contrast moments is determined; and the abnormal degree of the hazard of the natural gas combustion products is determined in combination with the hazard factor and the confidence level.

[0071] The concentration and composition of natural gas combustion products usually fluctuate greatly, which may be affected by external factors such as weather and industrial activities, so the hazard factors may not accurately reflect the long-term or actual environmental conditions; and the change in the concentration of natural gas combustion products may be only temporary, and the assessment at a single moment may not be able to capture long-term trends or certain potential hazards. For example, some pollutants may have a high concentration in a short period of time, but it does not mean that the degree of harm has always been the same, so a comprehensive analysis can be conducted in combination with historical data and data at the sampling time. Historical data provides fluctuations in the concentration of natural gas combustion products in different time periods, which can help evaluate the trend of hazard changes under different temperature environments; therefore, in the embodiment of the present invention, each sampling moment is compared with the natural gas combustion products at its historical moment, and the degree of abnormal hazard of the natural gas combustion products at each sampling moment is comprehensively judged.

[0072] In some embodiments, determining the abnormal degree of harmfulness of the natural gas combustion products, that is, the above step S300 can be performed by Figure 2 The steps shown achieve:

[0073] Step S310, dividing the historical moments into strong contrast moments and weak contrast moments according to the types of natural gas combustion products at different moments.

[0074] In the embodiment of the present invention, the preset historical parameter M=20, and the M sampling moments before the i-th sampling moment are taken as the historical moments of the i-th sampling moment.

[0075] Take any historical moment as the moment to be analyzed. When the type of natural gas combustion products corresponding to the moment to be analyzed is consistent with that at the current sampling moment, the moment to be analyzed is taken as a strong contrast moment; when the type of natural gas combustion products corresponding to the moment to be analyzed is inconsistent with that at the current sampling moment, the moment to be analyzed is taken as a weak contrast moment.

[0076] Step S320: dividing some weak contrast moments into strong contrast moments according to the constraint relationship between natural gas combustion products and the number of types of natural gas combustion processes at the weak contrast moments.

[0077] Since different types of natural gas combustion products are unstable due to mutual influence during the exhaust process, by obtaining the degree of mutual restraint between different types of natural gas combustion products, the confidence of comparison at different historical moments can be improved more accurately. When the number and position of extreme points of the concentration curves of two natural gas combustion products are closer, it means that there is a strong correlation between the concentration changes of the two natural gas combustion products, which means that the degree of mutual restraint between the jth natural gas combustion product and the lth natural gas combustion product has a direct and strong mutual influence relationship.

[0078] Moreover, when the different types of natural gas combustion products between the weak contrast moment and the i-th sampling moment have a greater degree of mutual restraint for the same type of natural gas combustion products, it means that the comparison reference of the weak contrast moment is not great; but when the mutual restraint for the same type of natural gas combustion products is smaller, it means that the main influence of the natural gas combustion products at the weak contrast moment and the i-th sampling moment is through the same type of gas, so the comparison reference of the weak contrast moment is greater. Therefore, by analyzing the mutual restraint between the two natural gas combustion products and the comparison reference of the weak contrast moment, some weak contrast moments can be re-divided and divided into strong contrast moments to participate in the analysis and calculation of subsequent steps.

[0079] In some embodiments, by analyzing the mutual restriction degree between the two natural gas combustion products and the comparison reference of the weak contrast moments, some weak contrast moments are divided into strong contrast moments, that is, the above step S320 can be performed by Figure 3 The steps shown achieve:

[0080] Step S321, analyzing the constraint relationship between the concentrations of different natural gas combustion products, and determining the correlation constraint degree between the different natural gas combustion products.

[0081] First, the least squares method is used to fit the concentration data of each natural gas combustion product at the historical moment corresponding to the sampling moment to obtain the historical concentration data curve. The concentration data of natural gas combustion products and The concentration data of natural gas combustion products were fitted by curve fitting to obtain the The historical concentration data curve of natural gas combustion products and the Historical concentration data curves of various natural gas combustion products.

[0082] For any two natural gas combustion products, the difference in the number of extreme value points of the historical concentration data curves of the two natural gas combustion products is analyzed to determine the constrained fluctuation difference; the time difference corresponding to the extreme values ​​of the same order in the concentration data curves of the two natural gas combustion products is calculated as the constrained time difference; the product value of the constrained fluctuation difference and the constrained time difference is negatively correlated and mapped to obtain the correlation constraint degree between the two natural gas combustion products.

[0083] In the embodiment of the present invention, the constrained fluctuation difference is: the absolute value of the difference in the number of extreme value points of the historical concentration data curves of the two natural gas combustion products.

[0084] In the embodiment of the present invention, taking the jth natural gas combustion product and the lth natural gas combustion product as an example, the mutual restriction degree between the jth natural gas combustion product and the lth natural gas combustion product is The calculation formula is:

[0085] ;

[0086] Among them, exp is an exponential function with a natural constant as the base; is the number of extreme value points in the historical concentration data curve of the j-th natural gas combustion product; is the number of extreme value points in the historical concentration data curve of the combustion products of the first type of natural gas; is the constraint fluctuation difference between the combustion products of the jth natural gas and the combustion products of the lth natural gas; is the time corresponding to the nth extreme point in the historical concentration data curve of the lth natural gas combustion product; is the time corresponding to the nth extreme point in the historical concentration data curve of the jth natural gas combustion product; is the constraint time difference between the jth natural gas combustion product and the lth natural gas combustion product.

[0087] Step S322, determining the comparison reference at the weak comparison moment according to the mutual restriction degree of the natural gas combustion products and the number of types of the natural gas combustion process at the weak comparison moment.

[0088] Taking the i-th sampling moment and the m-th weak contrast moment corresponding to the i-th sampling moment as an example, the comparison reference of the m-th weak contrast moment corresponding to the i-th sampling moment is The calculation formula is:

[0089] ;

[0090] Among them, norm is the normalization function; is the number of natural gas combustion products of the same type between the i-th sampling moment and the m-th weak comparison moment; is the number of different types of natural gas combustion products between the i-th sampling moment and the m-th weak comparison moment; is the mutual restriction degree between the ath natural gas combustion product of the same type and the bth natural gas combustion product of different type at the i-th sampling moment; is the mutual restriction degree between the a-th natural gas combustion product of the same type and the b-th natural gas combustion product of different type at the m-th weak contrast moment corresponding to the ith sampling moment; To take the absolute value sign.

[0091] The more the number of natural gas combustion products of the same type between the ith sampling moment and the mth weak contrast moment corresponding to the ith sampling moment is, the more similar the data characteristics between the ith sampling moment and the mth weak contrast moment corresponding to the ith sampling moment are; the closer the mutual restraint between the same type of natural gas combustion products and the different types of natural gas combustion products is, the more it indicates that the main influence of the two natural gas combustion products is through the same type of gas, and thus the comparison reference of the mth weak contrast moment is higher.

[0092] Step S323: when the contrast reference of the weak contrast moment is greater than or equal to the preset contrast threshold, the weak contrast moment is classified as a strong contrast moment.

[0093] In the embodiment of the present invention, the preset contrast threshold is 0.8, and in other embodiments, it can be adjusted by the implementer according to the actual situation. When the contrast reference of the mth weak contrast moment corresponding to the i-th sampling moment is greater than or equal to the preset contrast threshold, the mth weak contrast moment is recorded as a strong contrast moment. In this way, some weak contrast moments are divided into strong contrast moments.

[0094] Step S330, determining the confidence level of the strong contrast moment according to the time difference and temperature difference of the strong contrast moment.

[0095] When the temperature data at the strong contrast moment is consistent with the temperature data at the i-th sampling moment, it means that the contrast effect at this time is good. If the difference in the hazard factor of the natural gas combustion products between the strong contrast moment and the i-th sampling moment is greater, it means that the possibility of abnormality at the i-th sampling moment is greater; and when the temperature data at the strong contrast moment is inconsistent with the temperature data at the i-th sampling moment, it means that the contrast effect at this time is not ideal, and a weak contrast weight needs to be assigned. Therefore, by analyzing the difference in time and temperature, the confidence level of the strong contrast moment is determined, and the hazard factor is weighted by the confidence level to achieve the adjustment of the hazard factor.

[0096] The method for obtaining the confidence level of the strong contrast moment is: calculating the product of the time difference and the temperature difference between the strong contrast moment and the current moment as the initial deviation; performing negative correlation mapping on the initial deviation to obtain the confidence level of the strong contrast moment.

[0097] Taking the confidence level of the kth strong contrast moment corresponding to the i-th sampling moment as an example, the confidence level of the kth strong contrast moment corresponding to the i-th sampling moment is The calculation formula is:

[0098] ;

[0099] Among them, e is an exponential function with a natural constant as the base; is the time value of the kth strong contrast moment corresponding to the i-th sampling moment; is the time value of the i-th sampling moment; is the temperature data at the kth strong contrast moment corresponding to the i-th sampling moment; is the temperature data at the i-th sampling moment.

[0100] It should be noted that the time value corresponding to the sampling time and the strong contrast time here can be understood as the collection order value corresponding to the time.

[0101] Step S340, combining the hazard factor and the confidence level to determine the abnormal degree of hazard of the natural gas combustion products.

[0102] The average of the confidence levels at all strong contrast moments is used as the weighted value, and the sum of the hazard factors at all strong contrast moments is weighted to obtain the abnormal degree of hazard of natural gas combustion products.

[0103] Taking the i-th sampling moment as an example, the abnormal degree of hazard at the i-th sampling moment The calculation formula is:

[0104] ;

[0105] in, is the number of strong contrast moments at the i-th sampling moment; is the contrast confidence level of the kth strong contrast moment at the i-th sampling moment; is the number of types of all natural gas combustion products at the kth strong contrast moment at the i-th sampling moment; is the hazard factor of the jth natural gas combustion product at the kth strong contrast moment at the ith sampling moment.

[0106] Step S400, constructing an isolation tree of natural gas fuel products based on combustion product emission monitoring data; adjusting the path length of the isolation tree of natural gas fuel products based on the degree of hazard abnormality; obtaining the abnormal score of the natural gas combustion products corresponding to each data point through the isolation tree, and determining the abnormal data in the natural gas combustion products based on the abnormal score.

[0107] In the embodiment of the present invention, an isolation tree of natural gas fuel products is constructed based on temperature data during the emission process of natural gas combustion products included in the combustion product emission monitoring data of natural gas combustion products.

[0108] First, construct an isolation tree. In the process of natural gas combustion product emission, accurate identification of the abnormal degree of natural gas combustion product hazards is the key to timely discovering and handling potential problems. When processing such data, the traditional isolation forest algorithm regards the temperature data in the natural gas combustion product emission process at all sampling moments as equally important, which ignores the different roles of temperature data in different natural gas combustion product emission processes in anomaly detection. For example, when the temperature data in the natural gas combustion product emission process changes significantly, the abnormal degree of the monitoring data may be very high. If these temperature data in the natural gas combustion product emission process are placed at a higher level when constructing an isolation tree, they can isolate abnormal data points faster, thereby improving the accuracy of anomaly detection. Therefore, by giving a higher weight to the temperature data in the natural gas combustion product emission process with a high degree of abnormality and assigning it to an isolation tree at a higher level, the proportion of the path length calculated by the tree becomes larger.

[0109] An isolated tree is constructed based on the temperature data of the natural gas combustion product emission process at all sampling moments, wherein for the same isolated tree, the temperature data of the natural gas combustion product emission process of different dimensions are selected at different layers of the isolated tree for segmentation, and a segmentation point is randomly selected for each layer to divide the data into two parts, and this process is repeated recursively until a certain stop condition is met, such as the tree reaches a predetermined height, or the node contains only one data point, thereby completing the construction of different isolated trees. It should be noted that the method of constructing an isolated tree is a well-known technology for those skilled in the art and is not limited here.

[0110] After the isolation tree is constructed, the path length of the isolation tree of the natural gas fuel product is adjusted according to the abnormal degree of the hazard.

[0111] For any isolated tree, the root node of the isolated tree is defined as the 0th layer, and then it increases downwards in sequence, that is, the child nodes of the root node are located in the 1st layer, the child nodes of these child nodes are located in the 2nd layer, and so on. Get the path length to each data point in the isolated tree, that is, the number of edges from the root node to the data point.

[0112] The weighted path length of any data point in the isolated tree is calculated based on the path length of the data point corresponding to any natural gas combustion product in the isolated tree and the abnormality of the temperature data in the natural gas combustion product emission process on the layer where the data point is located.

[0113] More specifically: the negative correlation mapping value of the mean of the hazard abnormality degree of the layer to which the data point corresponding to each natural gas combustion product belongs in the isolation tree is used as a weighted value, and the path length of the data point corresponding to each natural gas combustion product in the isolation tree is weighted to obtain the weighted path length of the data point corresponding to each natural gas combustion product in the isolation tree, and the weighted path length is the path length of the isolation tree of the adjusted natural gas fuel product.

[0114] In some embodiments, the weighted path length is calculated as:

[0115] ;

[0116] in, is the weighted path length of the i-th data point in the h-th isolated tree; exp is an exponential function with a natural constant as the base; is the path length of the i-th data point in the h-th isolated tree; is the mean value of the abnormal degree of hazard of natural gas combustion products corresponding to the layer where the ith data point is located in the hth isolated tree.

[0117] The greater the degree of abnormality of the combustion product emission monitoring data corresponding to the layer where the data point is located, the greater the possibility that the data point is abnormal. In the traditional isolated tree, the smaller the path length, the more abnormal it is. Therefore, the weighted path length of the data point needs to be made smaller.

[0118] Since abnormal data points often deviate from the distribution pattern of normal data points, resulting in abnormal data points having shorter path lengths in isolated trees, the weighted path lengths of all data points in the isolated tree are used to replace the original path lengths of each data point to obtain the abnormal score of each data point. This ensures that those isolated trees that perform better in anomaly detection occupy a more important position in the final anomaly score calculation, thereby improving the accuracy of anomaly detection.

[0119] Take any sampling moment as the target sampling moment, and take the average of the abnormal scores of the corresponding data points of the combustion product emission monitoring data of all types of natural gas combustion product emission processes at the target sampling moment as the moment abnormal score of the target sampling moment; when the moment abnormal score is greater than or equal to the preset abnormal threshold, the combustion product emission monitoring data at the target sampling moment is determined to be suspected abnormal data. In the embodiment of the present invention, the preset abnormal threshold is 0.7, and in other embodiments, the implementer can adjust the value according to the actual situation.

[0120] That is, for the combustion product emission monitoring data of all types of natural gas combustion product emissions at any sampling moment, the abnormal scores of the corresponding data points of the combustion product emission monitoring data of all types of natural gas combustion products at the sampling moment are obtained through different isolated trees, and the mean of the abnormal scores of the corresponding data points at the sampling moment is taken as the moment abnormal score of the combustion product emission monitoring data at the sampling moment. The preset abnormal parameter LT=0.7, if the moment abnormal score of the combustion product emission monitoring data at the sampling moment is greater than or equal to the abnormal parameter LT, the combustion product emission monitoring data at the sampling moment is recorded as suspected abnormal data.

[0121] If the proportion of the number of suspected abnormal data in the combustion product emission monitoring data at the sampling moment and the combustion product emission monitoring data at the corresponding historical moment is greater than or equal to one-half, the combustion product emission monitoring data at the sampling moment is recorded as abnormal data. The historical moment here refers to the previous M sampling moments.

[0122] If the combustion product emission monitoring data is abnormal, it may indicate that the combustion efficiency of natural gas is low and the heat energy is not fully converted. The combustion conditions should be adjusted or the equipment should be repaired in time to optimize the combustion process of natural gas, reduce energy waste and improve the overall combustion efficiency.

[0123] An embodiment of the present invention provides a high-precision energy monitoring system, the system comprising:

[0124] A data monitoring module is used to obtain combustion product emission monitoring data during the emission of different types of natural gas combustion products;

[0125] A first data analysis module is used to determine the hazard factor of the natural gas combustion products according to the combustion product emission monitoring data of the natural gas combustion products;

[0126] The second data analysis module is used to divide the historical moments into strong contrast moments and weak contrast moments according to the types of natural gas combustion products at different moments; divide some weak contrast moments into strong contrast moments according to the constraint relationship between natural gas combustion products at weak contrast moments and the number of types of natural gas combustion processes; determine the confidence level of the strong contrast moments according to the time difference and temperature difference of the strong contrast moments; and determine the abnormal degree of the hazard of the natural gas combustion products in combination with the hazard factor and the confidence level;

[0127] The anomaly monitoring module is used to construct an isolation tree of natural gas fuel products based on combustion product emission monitoring data; adjust the path length of the isolation tree of natural gas fuel products according to the degree of hazard anomaly; obtain the anomaly score of the natural gas combustion products corresponding to each data point through the isolation tree, and determine the abnormal data in the natural gas combustion products based on the anomaly score.

[0128] Optionally, the transmission medium may be a wired link, such as but not limited to coaxial cable, optical fiber, and digital subscriber line, or a wireless link, such as but not limited to Wireless Fidelity (WIFI), Bluetooth, and mobile device network.

[0129] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0130] Figure 4 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 4 As shown, the computer device 500 includes: a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and running on the processor 520, wherein when the processor 520 executes the computer program 530, the computer device can execute any one of the high-precision energy anomaly monitoring data processing methods introduced above.

[0131] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a high-precision energy anomaly monitoring data processing method provided by an embodiment of the present invention.

[0132] The embodiment of the present invention can divide the functional modules of the device according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0133] In the case of dividing each module according to each function, the device may also include a signal uploading module, a determining module, an adjusting module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0134] It should be understood that the device provided in the embodiment of the present invention is used to execute the above-mentioned high-precision energy anomaly monitoring data processing method, and thus can achieve the same effect as the above-mentioned implementation method.

[0135] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the actions of the device. The storage module may be used to support the device to execute mutual program codes, etc. The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. The processor may also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0136] In addition, the device provided in an embodiment of the present invention may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a high-precision energy anomaly monitoring data processing method provided in the above embodiment.

[0137] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a high-precision energy anomaly monitoring data processing method provided by the above embodiment.

[0138] An embodiment of the present invention further provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement a high-precision energy anomaly monitoring data processing method provided in the above embodiment.

[0139] Among them, the device, computer-readable storage medium, computer program product or chip provided in the embodiments of the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Through the description of the above implementation methods, technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways.

[0140] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other divisions in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0141] It should also be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0142] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0143] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0144] The above contents are only specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A high-precision energy anomaly monitoring data processing method, characterized in that: The method comprises the following steps: Obtain combustion product emission monitoring data during the emission of different types of natural gas combustion products; Determine the hazard factors of natural gas combustion products based on the monitoring data of combustion product emissions of natural gas combustion products; According to the types of natural gas combustion products at different times, historical moments are divided into strong contrast moments and weak contrast moments; according to the constraint relationship between natural gas combustion products at weak contrast moments and the number of types of natural gas combustion processes, some weak contrast moments are divided into strong contrast moments; according to the time difference and temperature difference of strong contrast moments, the confidence level of strong contrast moments is determined; and the abnormal degree of hazard of natural gas combustion products is determined by combining the hazard factor and the confidence level; Based on the combustion product emission monitoring data, an isolation tree of natural gas fuel products is constructed; according to the abnormal degree of the hazard, the path length of the isolation tree of the natural gas fuel products is adjusted; the abnormal score of the natural gas combustion products corresponding to each data point is obtained through the isolation tree, and the abnormal data in the natural gas combustion products is determined according to the abnormal score.

2. A high-precision energy anomaly monitoring data processing method according to claim 1, characterized in that: The method of determining the hazard factors of the natural gas combustion products according to the combustion product emission monitoring data of the natural gas combustion products includes: The combustion product emission monitoring data includes: temperature data during the natural gas combustion product emission process, concentration data and activity values ​​of different types of natural gas combustion product gases; The temperature data, the activity value and the proportion of the concentration data in the concentration data of all natural gas combustion product gases are multiplied together, and the obtained product value is used as the hazard factor of the natural gas combustion product.

3. A high-precision energy anomaly monitoring data processing method according to claim 1, characterized in that: The historical moments are divided into strong contrast moments and weak contrast moments according to the types of natural gas combustion products at different moments, including: Take any historical moment as the moment to be analyzed. When the type of natural gas combustion products corresponding to the moment to be analyzed is consistent with that at the current sampling moment, the moment to be analyzed is taken as a strong contrast moment; when the type of natural gas combustion products corresponding to the moment to be analyzed is inconsistent with that at the current sampling moment, the moment to be analyzed is taken as a weak contrast moment.

4. A high-precision energy anomaly monitoring data processing method according to claim 1, characterized in that: According to the constraint relationship between the natural gas combustion products at the weak contrast moment and the number of types of the natural gas combustion process, some weak contrast moments are divided into strong contrast moments, including: Analyze the restriction relationship between the concentrations of different natural gas combustion products and determine the relevant restriction degree between different natural gas combustion products; According to the mutual restraint degree of natural gas combustion products and the number of types of natural gas combustion processes at the weak contrast moment, the comparison reference of the weak contrast moment is determined; When the contrast reference of the weak contrast moment is greater than or equal to the preset contrast threshold, the weak contrast moment is classified as a strong contrast moment.

5. A high-precision energy anomaly monitoring data processing method according to claim 4, characterized in that: The analyzing the restriction relationship between the concentrations of different natural gas combustion products and determining the relevant restriction degree between the different natural gas combustion products includes: For any two natural gas combustion products, the difference in the number of extreme value points of the historical concentration data curves of the two natural gas combustion products is analyzed to determine the constrained fluctuation difference; Calculate the cumulative sum of the time differences corresponding to the extreme values ​​of the same order in the concentration data curves of the two natural gas combustion products as the constrained time difference; A negative correlation mapping is performed on the product value of the constraint fluctuation difference and the constraint time difference to obtain the correlation constraint degree between the two natural gas combustion products.

6. A high-precision energy anomaly monitoring data processing method according to claim 4, characterized in that: The calculation formula of the comparison reference at the weak contrast moment is: ； Among them, norm is the normalization function; is the number of natural gas combustion products of the same type between the i-th sampling moment and the m-th weak comparison moment; is the number of different types of natural gas combustion products between the i-th sampling moment and the m-th weak comparison moment; is the mutual restriction degree between the ath natural gas combustion product of the same type and the bth natural gas combustion product of different type at the i-th sampling moment; is the mutual restriction degree between the a-th natural gas combustion product of the same type and the b-th natural gas combustion product of different type at the m-th weak contrast moment corresponding to the ith sampling moment; To take the absolute value sign.

7. A high-precision energy anomaly monitoring data processing method according to claim 1, characterized in that: Determining the confidence level of the strong contrast moment according to the time difference and temperature difference of the strong contrast moment includes: The product of the time difference and the temperature difference at the strong contrast moment and the current moment is calculated as the initial deviation degree; the initial deviation degree is negatively correlated and mapped to obtain the confidence level of the strong contrast moment.

8. The high-precision energy anomaly monitoring data processing method according to claim 1 is characterized in that: The step of adjusting the path length of the isolated tree of the natural gas fuel product according to the abnormal degree of the hazard includes: The mean value of the abnormal degree of hazard of the layer to which the data point corresponding to each natural gas combustion product belongs in the isolated tree is used as the negative correlation mapping value of the weighted value, and the path length of the data point corresponding to each natural gas combustion product in the isolated tree is weighted to obtain the weighted path length of the data point corresponding to each natural gas combustion product in the isolated tree. The weighted path length is the path length of the isolated tree of the adjusted natural gas fuel product.

9. A high-precision energy anomaly monitoring data processing method according to claim 1, characterized in that: Determining abnormal data in the natural gas combustion products according to the abnormality score includes: Taking any sampling moment as the target sampling moment, taking the average of the abnormal scores of the corresponding data points of the combustion product emission monitoring data of all types of natural gas combustion product emission processes at the target sampling moment as the moment abnormal score of the target sampling moment; when the moment abnormal score is greater than or equal to the preset abnormal threshold, the combustion product emission monitoring data at the target sampling moment is determined to be suspected abnormal data; If the proportion of suspected abnormal data in the combustion product emission monitoring data at the target sampling moment and the combustion product emission monitoring data at the corresponding historical moment is greater than or equal to one half, the combustion product emission monitoring data at the sampling moment shall be recorded as abnormal data.

10. A high-precision energy monitoring system, characterized in that: The system includes the following modules: A data monitoring module is used to obtain combustion product emission monitoring data during the emission of different types of natural gas combustion products; A first data analysis module is used to determine the hazard factor of the natural gas combustion products according to the combustion product emission monitoring data of the natural gas combustion products; The second data analysis module is used to divide the historical moments into strong contrast moments and weak contrast moments according to the types of natural gas combustion products at different moments; divide some weak contrast moments into strong contrast moments according to the constraint relationship between natural gas combustion products at weak contrast moments and the number of types of natural gas combustion processes; determine the confidence level of the strong contrast moments according to the time difference and temperature difference of the strong contrast moments; and determine the abnormal degree of the hazard of the natural gas combustion products in combination with the hazard factor and the confidence level; The anomaly monitoring module is used to construct an isolation tree of natural gas fuel products based on combustion product emission monitoring data; adjust the path length of the isolation tree of natural gas fuel products according to the degree of hazard anomaly; obtain the anomaly score of the natural gas combustion products corresponding to each data point through the isolation tree, and determine the abnormal data in the natural gas combustion products based on the anomaly score.

Images